English
Related papers

Related papers: Step-level Reward for Free in RL-based T2I Diffusi…

200 papers

Long-term temporal credit assignment is an important challenge in deep reinforcement learning (RL). It refers to the ability of the agent to attribute actions to consequences that may occur after a long time interval. Existing…

Machine Learning · Computer Science 2020-10-27 Tanmay Gangwani , Yuan Zhou , Jian Peng

Recent advances in diffusion-based text-to-image (T2I) models have led to remarkable success in generating high-quality images from textual prompts. However, ensuring accurate alignment between the text and the generated image remains a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jia Jun Cheng Xian , Muchen Li , Haotian Yang , Xin Tao , Pengfei Wan , Leonid Sigal , Renjie Liao

Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Dongzhi Jiang , Ziyu Guo , Renrui Zhang , Zhuofan Zong , Hao Li , Le Zhuo , Shilin Yan , Pheng-Ann Heng , Hongsheng Li

We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the…

Machine Learning · Computer Science 2025-08-12 Xuefeng Gao , Jiale Zha , Xun Yu Zhou

Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward…

Artificial Intelligence · Computer Science 2021-12-03 Charles Packer , Pieter Abbeel , Joseph E. Gonzalez

The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems. While traditional methods depend on the inherent knowledge of LLMs without fine-tuning, more recent approaches…

Artificial Intelligence · Computer Science 2024-12-10 Zhirui Deng , Zhicheng Dou , Yutao Zhu , Ji-Rong Wen , Ruibin Xiong , Mang Wang , Weipeng Chen

Reinforcement Learning (RL) heavily relies on the careful design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term Reinforcement Learning (LTRL) tasks remains a significant challenge. As a…

Machine Learning · Computer Science 2025-06-03 Qi Ju , Falin Hei , Zhemei Fang , Yunfeng Luo

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Artificial Intelligence · Computer Science 2024-10-29 Jiaxiang Li , Siliang Zeng , Hoi-To Wai , Chenliang Li , Alfredo Garcia , Mingyi Hong

Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. We argue that the denoising process is crucially limited by an accumulation of the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Hui Lu , Albert ali Salah , Ronald Poppe

Diffusion models have shown remarkable success in text-to-image generation, making preference alignment for these models increasingly important. The preference labels are typically available only at the terminal of denoising trajectories,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Dingyuan Shi , Yong Wang , Hangyu Li , Xiangxiang Chu

Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimization with such reward models, which serve as mere proxy…

Machine Learning · Computer Science 2024-04-03 Kyuyoung Kim , Jongheon Jeong , Minyong An , Mohammad Ghavamzadeh , Krishnamurthy Dvijotham , Jinwoo Shin , Kimin Lee

Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video…

Robotics · Computer Science 2025-10-28 Mateo Clemente , Leo Brunswic , Rui Heng Yang , Xuan Zhao , Yasser Khalil , Haoyu Lei , Amir Rasouli , Yinchuan Li

Diffusion models have recently demonstrated exceptional performance in image generation task. However, existing image generation methods still significantly suffer from the dilemma of image reasoning, especially in logic-centered image…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Jiadong Pan , Zhiyuan Ma , Kaiyan Zhang , Ning Ding , Bowen Zhou

Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing methods, however, suffer from slow convergence during…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Seunghyun Lee , Tae-Kyun Kim

Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. However, existing approaches face a fundamental credit assignment problem: methods like…

Computation and Language · Computer Science 2026-04-02 Chris Samarinas , Haw-Shiuan Chang , Hamed Zamani

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yushi Huang , Xiangxin Zhou , Ruoyu Wang , Chi Zhang , Jun Zhang , Tianyu Pang

Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforcement learning.…

Robotics · Computer Science 2026-05-08 Xunlan Zhou , Xuanlin Chen , Shaowei Zhang , ShengHua Wan , Xiaohai Hu , Lei Yuan , De-chuan Zhan

Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior. In this work, we explore a simple inference-time…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Anuj Singh , Sayak Mukherjee , Ahmad Beirami , Hadi Jamali-Rad

Benefiting from pre-trained text-to-image (T2I) diffusion models, real-world image super-resolution (Real-ISR) methods can synthesize rich and realistic details. However, due to the inherent stochasticity of T2I models, different noise…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Rongyuan Wu , Lingchen Sun , Zhengqiang Zhang , Shihao Wang , Tianhe Wu , Qiaosi Yi , Shuai Li , Lei Zhang

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, one first trains a reward model (RM) on…

Machine Learning · Computer Science 2025-10-20 Gokul Swamy , Sanjiban Choudhury , Wen Sun , Zhiwei Steven Wu , J. Andrew Bagnell